Seeing bruises under the skin: NIR vs SWIR on apples
Two supplied images of the same apple compare 940 nm near-infrared and 1550 nm short-wave infrared. The 1550 nm capture shows stronger dark patches at the marked bruises, illustrating why wavelength choice matters.
Match the wavelength, sensor and optics as one system.
Real camera capture
- NIR940 nm
- SWIR1550 nm
- CameraInGaAs, 900–1700 nm
- ResultBruises dark and wide at 1550 nm
Lighting application-lab image sheet
What the camera saw
Cropped from the source test sheet; original test annotations are retained. Captures are not generated or enhanced. Drag a comparison slider, or open any image full size.
SWIR 1550 nm: SWIR 1550 nm: two dark bruises with clear borders (marked by the tester).
The challenge
The colour photograph shows little obvious surface damage. The inspection problem is to find damage that has weak visible contrast.
Near-infrared at 940 nm goes a little deeper and shows one soft area, but the contrast is low and the second bruise is missed.
How it was solved
Changing wavelength changes the relative absorption and scattering of light in the fruit. This application compares 940 nm with 1550 nm; tissue and moisture differences can affect that contrast.
The test imaged the same apple at 940 nm and at 1550 nm. At 1550 nm both bruises show as dark patches with clear borders, including one at the top that the 940 nm image misses.
Why it works
- 1
The supplied 1550 nm capture shows stronger bruise contrast on this apple. Cultivar, maturity and time since damage need separate validation.
- 2
The proposed SWIR camera and lens cover the required band. A standard visible-only camera cannot be assumed to work at 1550 nm.
- 3
The purple light paths in the 3D scene are a visual convention for invisible infrared; they do not depict a visible purple source or measured penetration.
Lighting application-lab image sheet
Evidence you can inspect
The annotated 1550 nm image shows two dark regions more distinctly than the 940 nm image.
The sheet labels the wavelengths as 940 nm and 1550 nm; it supplies no sorting accuracy or bruise-depth data.
One illustrated sample. Confirm contrast across your fruit varieties, ripeness and damage ages.
From image contrast to a production decision
What to validate on your part
- 01
Cover real variation
Test varieties, ripeness, surface moisture and different times after damage.
- 02
Match the complete spectral path
Verify the light wavelength, lens transmission, filters and sensor response together.
- 03
Check movement
Set exposure and trigger timing using fruit moving at the intended conveyor speed.
From the demo to your test bench
Parts in this setup
LightOur pick
LS-RN9090-SWIR
Short wavelength infrared light, Ø90 mm (LS-RN9090-SWIR)
Ring light from the same SWIR series as the test (seven wavelengths, 1050 to 1650 nm); ask for 1550 nm. 90 mm outside, 40 mm inside.Wavelength: 1550 nm
Configuration to confirm
Separate test / alternative
LightOur pick
LS-4BRH15016-SWIR
Short wavelength infrared light, 162 x 22 x 36 mm (LS-4BRH15016-SWIR)
Two SWIR bars proposed for lighting both sides of the fruit. Specify 1550 nm in this custom configuration; the family SKU alone does not select a wavelength. Validate illumination coverage and exposure on the sample.Wavelength: 1550 nm
Configuration to confirm
In proposed setup · quantity 2
CameraOur pick
MV-CI013-GS-NN
Hikrobot MV-CI013-GS-NN 1.3MP SWIR Camera, IMX990, GigE, fanless
1.3 MP InGaAs SWIR camera (Sony IMX990, 5 µm pixels), C-mount, fanless.
Price on request
In proposed setup
LensOur pick
LS-KF2514M-5MP-NIR-V2
25mm, F1.4, 1", 900-1700nm, C-mount, SWIR lens (LS-KF2514M-5MP-NIR-V2)
25 mm F1.4 C-mount lens with a 900–1700 nm coating range and a printed 0.38 m minimum object distance. The proposed 400 mm lens-to-part spacing is illustrative; confirm focus and field on the actual sample.
$449.00
In proposed setup
Camera test stationOur pick
LS-BT-XZ-G-8-6045
Camera stand with XZ adjustment and glass tray, height 800 mm (LS-BT-XZ-G-8-6045)
800 mm column, 600 × 450 mm breadboard, XZ adjustment, glass tray and two lighting holders as listed. Proposed for the SWIR lens focusing distance and camera assembly; confirm loads, travel and camera/lens clamps.
$359.00
In proposed setup
"Tested" identifies the part named in the source. "Our pick" is a proposed alternative or supporting part. Confirm colour, optics, controllers, power supplies, cables and mounting before ordering.
The set-up
| Light | SWIR LED light, 1550 nm (and 940 nm for comparison) |
|---|---|
| Camera | InGaAs SWIR area scan |
| Lens | SWIR-corrected, 900–1700 nm |
| Mounting (proposed) | LS-BT-XZ-G-8-6045 · camera test station with glass tray and two lighting holders |
| Proposed lens focusing limit | Printed minimum object distance 0.38 m; illustrated lens-to-part spacing 400 mm |
| Illustrative viewing region | 90 × 72 mm; not the source field or a verified lens field specification |
Mount the optics with intent
The station is an optical test bench, with its two lighting holders included in the catalog listing. The 3D column and base follow the published height and footprint. Carriages, clamps and part supports are schematic: confirm camera screw pattern, lens support, light fasteners, permissible load and actual travel before ordering.
Complete the electrical system
Select a controller against the exact light voltage, drive mode and power, then confirm camera data/power/I/O cables and a suitable PC. These are not silently added to the proposed optical kit.
Build this system
Start from this setup, adapt it to your part.
The configurator opens with this study's camera, lens, light and station picked. Swap any part, check fit and price, then buy or ask for a quote.
Camera and available lens CAD are published models. Lens and light envelopes use printed dimensions. The linked station uses its published base size and column height; carriage, brackets, fittings, parts and spacing are illustrative. Confirm load, travel, fasteners and clearances before ordering. Light paths explain the arrangement and do not simulate optical performance. The 400 mm lens-to-part spacing respects the printed 0.38 m minimum object distance. The drawn 90 × 72 mm viewing region is illustrative and needs confirmation by focusing and calibration; it is not a measured source field.
Food, pharma and agriculture
Related case studies
Food, pharma and agriculture
Contamination in blister packs
Reduce glare before searching for a dark speck.LightArch shadowless, 125 × 70 mm emittingExplore the study
Food, pharma and agriculture
Bread-piece outline and orientation
A usable outline is the first step; prove the handling task on real product variation.Light in sourceLS-2BS28238-RGBW · redExplore the study
Food, pharma and agriculture
Fruit colour under two source lighting conditions
A colour threshold needs controlled capture and a defined reference.Proposed light housing (spec)162 × 36 × 26 mmExplore the study
Make the next trial specific.
Tell us the part size, smallest defect or tolerance, available working distance, material and line speed. Include what a good part and a reject look like.
About this case study: the photos and camera images come from the application laboratory of the maker of the lighting and optics we sell, imaged on the parts shown; your results depend on your part, camera and set-up. This is an application-lab study, not a LumaSpec customer deployment. Source figures are reported results; proposed components require a fresh trial. The 3D scene illustrates the arrangement and does not simulate imaging performance.